Entdecken Sie die neuesten Updates von CometAPI mit leistungsstarken KI-Modellen für die Erstellung von Bildern, Videos und Musik. Entfesseln Sie noch heute Ihre Kreativität!
Alle Modelle ansehenCometAPI
CometAPI Adds Qwen3.8-Flash
Model ID: qwen3.8-flash
Qwen3.8-Flash is Qwen’s latest multimodal large model, combining powerful understanding and generation capabilities with fast response performance. It natively supports million-token context windows, enabling it to process ultra-long documents, code repositories, and complex conversations in a single request.
Supported Endpoint
qwen3.8-flash: Chat API formatCometAPI Adds Wan 3.0
Model ID: wan3.0
CometAPI now supports Wan 3.0, providing developers with access to its latest video generation capabilities.
Supported Endpoint
wan3.0: Video API formatCometAPI Adds GLM-5.3-Flash with a Limited-Time 50% Discount
Model ID: glm-5.3-flash
GLM-5.3-Flash is the first native multimodal model in the GLM-5 series, delivering stronger intelligence than GLM-5.2 while maintaining a highly cost-efficient architecture.
Promotional Pricing
GLM-5.3-Flash is now available at 50% off the standard list price.
The promotion ends at 24:00 on September 9, 2026 (UTC+8, Singapore Time), equivalent to 16:00 UTC on September 9, 2026.
Supported Endpoint
glm-5.3-flash: Chat API formatGPT-5.6 Sol Promotional Pricing Update
Model ID: gpt-5.6-sol
Following the latest official price reduction, CometAPI is offering an additional 20% discount on GPT-5.6 Sol API usage.
CometAPI Promotional Pricing
The promotional pricing takes effect immediately and is valid through November 21, 2026.
Supported Endpoint
gpt-5.6-sol: Responses API formatCometAPI Adds DeepSeek V4 Flash Vision and Grok Imagine Models
Model IDs:
deepseek-v4-flash-visiongrok-imagine-image-2.0grok-imagine-video-1.5CometAPI now supports DeepSeek’s latest vision model, along with Grok Imagine models for image and video generation.
Additional Service Updates
minimax-h3 integration has been optimized to support its latest capabilities.deepseek-v4-flash and deepseek-v4-pro have been adjusted in sync with the official DeepSeek service. These changes take effect immediately.Supported Endpoint
deepseek-v4-flash-vision: Chat API formatgrok-imagine-image-2.0: Grok Image API formatgrok-imagine-video-1.5: Grok Video API formatminimax-h3: Video API formatModel IDs:
qwen3.8-2.4t-a95bminimax-m3qwen3.8-2.4t-a95b is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max. It is suited for coding, research, complex reasoning, and agentic workflows.
MiniMax M3 pricing has been reduced to 50% of the official list price, following the official pricing update.
Effective Time
MiniMax M3 pricing update is effective immediately.
Supported Endpoint
Chat API format
Developer Documentation
Model ID:
gemini-3.7-flashgemini-3.7-flash delivers substantial improvements across software engineering, knowledge work, and web development workflows, with an introductory price of half the original Gemini 3.6 Flash cost per million tokens.
Developer Documentation
Gemini Content Generation API Guide
Model IDs:
glm-5.3flux-3Overview
glm-5.3 is a next-generation open-source large language model optimized for complex coding, long-horizon tasks, and cybersecurity scenarios, with significantly improved coding and agent performance over GLM-5.2.
flux-3 represents a new generation of real-world multimodal flow models, advancing visual intelligence with stronger multimodal understanding and generation quality.
Supported Formats
Chat API format
Video API format
Developer Documentation
Model IDs:
deepseek-v4-pro-0813grok-4.6Overview
deepseek-v4-pro-0813 is DeepSeek’s GA release of V4 Pro, a large-scale mixture-of-experts model for advanced reasoning and professional workloads.
grok-4.6 is SpaceXAI’s smartest model, delivering frontier performance for coding, knowledge work, and STEM tasks.
Supported Format
Chat API format
Developer Documentation
Model ID:
seedance-2-5seedance-2-5 is a next-generation audio-video joint generation model built for 30-second storytelling, with precise reference control and powerful editing capabilities.
Supported Format
Video API format
Developer Documentation
Model ID:
minimax-h3minimax-h3 is a new video generation model designed for high-quality creative production. It delivers improved prompt understanding, stronger visual consistency, smoother motion, and more flexible reference-image control for cinematic video generation workflows.
Developer Documentation
Model ID:
qwen3.8-maxqwen3.8-max is Qwen’s MoE flagship model with 2.4T parameters, delivering major improvements in programming, office workflows, and professional task execution.
It supports autonomous programming, complete project delivery, native visual understanding, ultra-long document and video analysis, and long-term task planning with closed-loop iteration.
Supported Format
Chat API format
Developer Documentation
Model IDs:
gpt-5.6-lunagpt-5.6-terraCometAPI has reduced the price of GPT-5.6 Luna by 80% and GPT-5.6 Terra by 20%.
Effective Time
Effective immediately.
Model ID:
kimi-k3Kimi K3 resources are now stable, and the price has been reduced to 80% of the official list price.
Effective Time
Effective immediately.
CometAPI will update KLING pricing to align with the official KLING API list prices. Applicable account and group discounts will continue to be reflected on the Models page.
Effective Time
2026-07-29 09:00 Beijing Time
2026-07-29 01:00 UTC
Affected KLING Scenarios
Image generation and editing, Omni image generation, video generation, video effects, audio generation, TTS, lip-sync, avatar video, virtual try-on, image expansion, and recognition.
No API endpoint, request format, model ID, or task polling flow will change.
Model ID:
claude-opus-5claude-opus-5 is now available on CometAPI for advanced coding and complex reasoning workloads.
Supported Formats
Chat API format
Messages API format
Developer Documentation
Model IDs:
grok-imagine-imagegrok-imagine-image-qualityOverview
grok-imagine-image is a cost-efficient image generation and editing model for fast image creation, aspect-ratio control, and reference-image workflows.
grok-imagine-image-quality is the higher-quality Grok Imagine image model for detailed image generation and editing, with support for 1K and 2K output resolutions.
Image Generation
curl -sS https://api.cometapi.com/v1/images/generations \
-H "Authorization: Bearer $COMET_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "grok-imagine-image-quality",
"prompt": "A clean red geometric logo on a white background",
"aspect_ratio": "1:1",
"resolution": "2k",
"n": 1,
"response_format": "url"
}'
Image Editing
curl -sS https://api.cometapi.com/v1/images/edits \
-H "Authorization: Bearer $COMET_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "grok-imagine-image-quality",
"prompt": "Render this image as a pencil sketch",
"image": {
"url": "https://docs.x.ai/assets/api-examples/images/style-realistic.png",
"type": "image_url"
},
"resolution": "1k",
"n": 1,
"response_format": "url"
}'
Model IDs:
gemini-3.5-flash-litegemini-3.6-flashOverview
gemini-3.5-flash-lite is a low-latency, cost-effective multimodal model optimized for high-throughput and low-cost workloads.
gemini-3.6-flash provides frontier-level intelligence with higher speed and lower cost, designed for real-world tasks and agentic workflows.
Supported Formats
Chat API format
Gemini Content Generation API format
Developer Documentation
Model ID:
kimi-k3kimi-k3 is Kimi’s flagship model, designed for long-range programming and end-to-end knowledge work. It features a 1M token context window and leading-edge comprehensive intelligence.
Developer Documentation
Quick Integration Guide (Chat Format)
Following upstream lifecycle changes and updates to the CometAPI model catalog, the following models will be retired according to the schedule below.
| Deprecated Model | Retirement Date | Recommended Replacement |
|---|---|---|
| DeepSeek models outside the V4 series | 2026-07-17 | deepseek-v4-flash / deepseek-v4-pro |
| Qwen3.5 series | 2026-07-17 | qwen3.7-plus / qwen3.7-max / qwen3.6-plus |
| Qwen3 series | 2026-07-17 | qwen3.7-plus / qwen3.7-max / qwen3.6-plus |
| doubao-seedance-1-0-pro | 2026-07-17 | doubao-seedance-2-0 / doubao-seedance-2-0-fast |
| doubao-seed-1-8 | 2026-09-21 | doubao-seed-2-1-turbo-260628 / doubao-seed-2-1-pro-260628 |
| doubao-seedance-1-5-pro | 2026-09-21 | doubao-seedance-2-0 / doubao-seedance-2-0-fast |
Each model will become unavailable after 23:59 on its listed retirement date.
Some routes may experience capacity limits or become unavailable earlier due to upstream lifecycle and capacity adjustments. Please complete migration and production validation in advance.
Model IDs:
gpt-5.6gpt-5.6-solgpt-5.6-terragpt-5.6-lunaOverview
The GPT-5.6 series is now available on CometAPI with support for both Chat and Responses API formats.
gpt-5.6-sol and gpt-5.6 are flagship models for complex reasoning and coding.
gpt-5.6-terra balances intelligence and cost for general-purpose workloads.
gpt-5.6-luna is designed for cost-sensitive, high-volume use cases.
Developer Documentation
Model ID:
grok-4.5CometAPI now supports grok-4.5 in chat format. It is our flagship model for coding, agentic tool use, low-hallucination responses, configurable reasoning, and general-purpose workflows.
Developer Documentation:
https://apidoc.cometapi.com/api/text/chat
Model ID:
seedream-5-0-pro-260628CometAPI now supports seedream-5-0-pro-260628 for image generation. Seedream 5.0 Pro is built for high-precision generation scenarios, with improved control over composition, positioning, and visual elements. It supports text-to-image generation, single-image reference generation, and multi-image reference generation.
Developer Documentation:
https://apidoc.cometapi.com/api/image/seededit-seedream/bytedance-image-generation
Following upstream Azure OpenAI model lifecycle updates, the following Azure-backed GPT-4 series models have entered the Deprecated stage and are scheduled for retirement in October 2026.
Impact Time: Starting from 2026-07-08, subject to actual upstream provider availability and change timing.
| Deprecated Model | Retirement Date | Recommended Replacement |
|---|---|---|
| gpt-4o | 2026-10-01 | gpt-5.1 / gpt-5-mini |
| gpt-4o-mini | 2026-10-01 | gpt-5-mini |
| gpt-4.1 | 2026-10-14 | gpt-5.1 / gpt-5-mini |
| gpt-4.1-mini | 2026-10-14 | gpt-5-mini |
| gpt-4.1-nano | 2026-10-14 | gpt-5-mini |
Some legacy Azure OpenAI routes may become capacity-limited or unavailable before the official retirement date. Please migrate production traffic in advance to avoid service interruption.
Model ID:
claude-fable-5Access to claude-fable-5 has been restored. It brings 5th-generation intelligence to ambitious coding and professional workflows.
Developer Documentation
Model IDs:
gemini-3.1-flash-lite-imageclaude-sonnet-5gemini-3.1-flash-lite-image is an efficient image generation model designed for ultra-low latency and cost-effective image generation and editing.claude-sonnet-5 is a high-performance model for coding and agent workflows.Developer Documentation
Gemini Image Generation API Guide
Anthropic Messages API Guide
We now integrate HappyHorse 1.1 & Update Kling 3.0 and Kling 3.0 Omni
HappyHorse 1.1 (happyhorse-1.1): Significant upgrades in motion smoothness, multi-reference consistency (up to 9 images), prompt adherence for complex scenes, facial realism, and native audio-video synchronization with multilingual lip-sync. Ideal for production-quality short videos, branding, e-commerce, and storytelling.
Kling 3.0（kling-3.0 and kling-3.0-omni）: Advanced multimodal capabilities with Omni One architecture, director-level camera control, physics-aware motion, multi-shot storytelling, and native audio for hyper-realistic 1080p/4K cinematic output.
Access both via one unified OpenAI-compatible API. Perfect for cinematic shorts, ads, e-commerce, and storytelling.
Read our new blog comparing What is HappyHorse 1.1 and HappyHorse 1.1 vs 1.0:
Sign up for free credits → cometapi.com
Developer Documentation
[HappyHorse Video API Guide](https://apidoc.cometapi.com/api/video/happyhorse/create)
[Kling Text-to-Video API Guide](https://apidoc.cometapi.com/api/video/kling/text-to-video)
Model IDs:
doubao-seed-2-1-pro-260628doubao-seed-2-1-turbo-260628doubao-seed-evolvingOverview
doubao-seed-2-1-pro-260628 is a next-generation production-ready model with upgraded coding, agent, and multimodal capabilities for complex enterprise tasks.
doubao-seed-2-1-turbo-260628 balances performance and cost, with upgraded coding, agent, and multimodal capabilities for real-world complex tasks.
doubao-seed-evolving is designed for coding and agent scenarios, delivering weekly capability updates through a unified model ID.
Developer Documentation
Model ID:
glm-5.2GLM-5.2 supports a 1M context window, 128K max output, streaming tool-call output, forced deep thinking, and improved coding and reasoning capabilities.
Pricing
| Model | Input | Output |
|---|---|---|
| GLM 5.2 | $1.12/M | $3.528/M |
| GLM 5.1 | $1.12/M | $3.528/M |
Developer Documentation
Developer Documentation
📚 Developer Documentation
📚 Developer Documentation
Impact Time: 2026-09-08, subject to the actual change time.
To continuously improve service quality and optimize underlying model resources, CometAPI will delist the following Qwen models on 2026-09-08. Please switch to the recommended replacement models in advance.
| Deprecated Model | Recommended Replacement |
|---|---|
| qwen3.6-max-preview | qwen3.7-max |
| qwen3-max-preview | qwen3.7-max |
| qwen3-max | qwen3.7-max |
| qwen3-coder-plus | qwen3.7-plus |
/v1/videos✨ Feature Update
CometAPI now supports several new video generation models, including wan2.6, wan2.7, happyhorse-1.0, viduq3-turbo, and viduq3. These models support the /v1/videos API format. Pricing varies by model and resolution and is billed by generated video duration, in USD / second.
| Model Series | Supported Resolutions | Pricing |
|---|---|---|
wan2.6 / wan2.7 series | 720p, 1080p | Billed per second |
happyhorse-1.0 | 720p, 1080p | Billed per second |
viduq3 / viduq3-turbo series | 360p, 540p, 720p, 1080p | Billed per second |
minimax-m3 Model Now Available✨ Model Update
CometAPI now supports the minimax-m3 model.
📚 Developer Documentation
/v1/chat/completions✨ Adjustment Details
Due to ongoing resource stability challenges with the veo3 series, Comet will adjust the resource channels and billing rules for the veo3 series.
Previously, the veo3 series was billed per generation. It will now be adjusted to official same-price per-second billing, with the website’s default 20% discount applied.
| Model | Resolution | Official Per-second Price |
|---|---|---|
veo3.1 | 720p | $0.4 / second |
veo3.1 | 1080p | $0.4 / second |
veo3.1 | 4K | $0.6 / second |
veo3.1-fast | 720p | $0.1 / second |
veo3.1-fast | 1080p | $0.12 / second |
veo3.1-fast | 4K | $0.3 / second |
For example, when generating a 1080p video with veo3.1, the price after the 20% discount is:
$0.4 × 0.8 = $0.32 / second
For detailed pricing and available groups, please refer to the model details page: https://www.cometapi.com/models/
📚 Developer Documentation
CometAPI now supports Midjourney V8. When using the Midjourney image generation API, you can enable V8 by adding the --v 8 parameter directly in the prompt.
For more details about the Midjourney image generation API, please refer to the documentation:
https://apidoc.cometapi.com/api/image/midjourney/imagine
Following official model updates and iterations, Comet will retire the following models. Please switch to the latest available models as soon as possible.
Details page: https://www.cometapi.com/models/
| Deprecated Models |
|---|
glm-4.x series |
kimi-k2 series |
minimax-m2.1 |
minimax-m2 |
o1-mini |
gpt-3.5-turbo |
gemini-3.1-flash-lite-preview |
gemini-3-pro-preview |
gemini-2.5-flash-preview-09-25 |
gemini-2.5-flash-lite-preview-09-2025 |
gemini-2.5-flash-image-preview |
| Deprecated Models |
|---|
claude-opus-4 |
claude-sonnet-4-20250514 |
| Deprecated Models |
|---|
gpt-5-codex |
gpt-5.1-codex |
gpt-5.2-codex |
gpt-5-chat-latest |
gpt-5.1-chat-latest |
gpt-5.2-chat-latest |
gpt-4o-realtime |
gpt-realtime-mini |
gpt-audio-mini |
gpt-4o-mini-search-preview |
| Deprecated Models |
|---|
o4-mini |
gpt-4.1-nano |
o1-pro |
o3-mini |
📚 Supported Endpoints
/v1/chat/completions) ｜ Reference Guide📚 Supported Endpoints
/v1/chat/completions) ｜ Reference Guide/v1beta/models/{model}:{operator}) ｜ Reference Guide📅 2026-05-06
✨ Change Details
grok-4.3 is now live — excels at autonomous reasoning, knowledge work, and tool use. Ideal for complex agent workflows and deep analysis tasks.🍡 Recommended Models
grok-4.3📚 Developer Documentation
/v1/chat/completions).✨ Pricing Changes
grok-4.2 series pricing has been reduced to match grok-4.3 pricing.✨ Change Details
| Deprecated Model | Recommended Replacement |
|---|---|
grok-4-1-fast-reasoning | grok-4.3 |
grok-4-1-fast-non-reasoning | grok-4.20-non-reasoning |
grok-4-fast-reasoning | grok-4.3 |
grok-4-fast-non-reasoning | grok-4.20-non-reasoning |
grok-4-0709 | grok-4.3 |
grok-code-fast-1 | grok-4.3 |
grok-4.3; Non-reasoning models → grok-4.20-non-reasoning.📅 2026-04-29
✨ Change Details
deepseek-chat and deepseek-reasoner model families are being phased out and will cease API service.deepseek-v4-flashdeepseek-v4-pro🍡 Recommended Models
deepseek-v4-flash, deepseek-v4-pro📚 Developer Documentation
/v1/chat/completions).✨ Pricing Changes
| Model | Before (List) | After (List) | Discounted |
|---|---|---|---|
doubao-seedream-4-5-251128 | $0.04 / image | $0.04 / image (unchanged) | $0.032 / image |
doubao-seedream-4-0-250828 | $0.03 / image | $0.04 / image | $0.032 / image |
doubao-seedream-5-0-260128 | $0.035 / image | $0.04 / image | $0.032 / image |
gpt-5.5gpt-5.5-progpt-5.5-all / gpt-5.5-medium-all / gpt-5.5-high-all / gpt-5.5-xhigh-all / gpt-5.5-low-allgpt-image-2-all (Multimodal and image generation model)/v1/chat/completions): Supports multimodal inputs (image-to-image) and complex instructions. ⚠️ Note: supports stream: true only. Reference Guide/v1/images/generations): Supports standard text-to-image generation. Reference Guide📚 Developer Documentation
/v1/chat/completions).📚 Supported Endpoints
This model supports following standard OpenAI format:
/v1/images/generations): Supports standard text-to-image generation.Reference GuideThe legacy Seedance-series official API format is deprecated. All Seedance models (including
doubao-seedance-1-5-proanddoubao-seedance-1-0-pro) should now use the unifiedv1/videosendpoint going forward.Note:
doubao-seedance-1-5-proanddoubao-seedance-1-0-prodo not support image-to-video (input_referenceis not available for these models).
| Parameter | Description |
|---|---|
| Duration (seconds) | 4–15 seconds, default 5 |
| Aspect Ratio (size) | 21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16, default 16:9 |
| Resolution (resolution) | 480p / 720p / 1080p*, default 720p |
*1080p only available for
doubao-seedance-1-5-proanddoubao-seedance-1-0-pro
curl --location --request POST 'https://api.cometapi.com/v1/videos' \
--header 'Authorization: sk-your-key' \
--header 'Content-Type: multipart/form-data' \
--form 'prompt="a cat running on the beach"' \
--form 'model="doubao-seedance-2-0"' \
--form 'seconds="5"' \
--form 'size="16:9"' \
--form 'resolution="720p"' \
--form 'input_reference=@"your_image.png"'
💡
input_referenceis optional — include a reference image for image-to-video, or omit it for text-to-video. Only supported bydoubao-seedance-2-0anddoubao-seedance-2-0-fast.
For full API details, please refer to: https://apidoc.cometapi.com/api/video/seedance/create
📚 Developer Documentation
Set the request parameter mv to chirp-fenix.
{
"mv": "chirp-fenix",
"gpt_description_prompt": "cat"
}
🔹 gpt-5.4-mini
🔹 gpt-5.4-mini-2026-03-17
🔹 gpt-5.4-nano
🔹 gpt-5.4-nano-2026-03-17
gpt-5.4-mini, gpt-5.4-mini-2026-03-17: OpenAI's most powerful small model to date. It brings the capabilities of GPT-5.4 to a faster, more efficient architecture, designed specifically for coding, computer operations, and high-volume workloads.
gpt-5.4-nano, gpt-5.4-nano-2026-03-17: The most affordable GPT-5.4 class model, designed specifically for simple, massive-scale tasks where speed and cost are prioritized (such as classification, data extraction, and sorting).
🔹 glm-5-turbo
🔹 qwen3.5-122b-a10b
🔹 qwen3.5-27b
🔹 qwen3.5-35b-a3b
🔹 qwen3.5-flash
To ensure service stability and manage storage costs, logs on this site will only be retained for 3 months. Expired logs will be automatically deleted and cannot be recovered!
If you need long-term retention, please download or back up your logs within 3 months!
Thank you for your understanding and support!
grok-4.20-beta series: Grok 4.20 Beta is X.ai's newest flagship model with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherence, delivering consistently precise and truthful responses.
grok-4.20-multi-agent-beta-0309:
reasoning.effort: medium, high, xhigh.
reasoning.effort supports the following options: none (default), low, medium, high, and xhigh.
📚 Developer Documentation
🔹 gemini-3.1-flash-lite-preview
🔹 gemini-3.1-flash-lite
gemini-3.1-flash-lite is the most cost-effective model in the Gemini series, optimized for high-volume agent tasks, translation, and simple data processing.📚 Developer Documentation
duration (e.g., 5s, 10s), aspect_ratio (e.g., 16:9, 1:1), and resolution (e.g., 720p) via simple parameters.request_id immediately upon submission; use the GET endpoint to check status and retrieve the generated video.🚀 Nano Banana 2 (Gemini 3.1) Flagship Image Model Released!
Designed for professional workflows, integrating reasoning with high-fidelity illustration.
💎 Available Models:
gemini-3.1-flash-image-preview
gemini-3.1-flash-image
🔥 Core Evolutions:
🔗 Integration Docs:
https://apidoc.cometapi.com/gemini-image-generation
📘 Usage Guide:
https://apidoc.cometapi.com/guide-nanobanana
⚠️ Important Migration Notice: Gemini 3 Pro Deprecation
Affected Models: gemini-3-pro-preview, gemini-3-pro-preview-thinking
Current Status: ❌ Deprecated
Shutdown Date: March 9, 2026
🚨 Action Required: To avoid service interruption, please migrate to Gemini 3.1 Pro Preview as soon as possible.
doubao-seedream-5-0-260128 - Doubao-Seedream-5.0-lite is ByteDance's latest image generation model. This model is the first to feature web retrieval capabilities, integrating real-time online information to enhance the timeliness of generated images. Additionally, the model's intelligence has been upgraded, enabling it to accurately parse complex prompts and visual content. Furthermore, it boasts enhancements in the breadth of world knowledge, reference consistency, and generation quality for professional scenarios, better satisfying enterprise-level visual creation needs.
doubao-seedream-5-0-260128📚 Developer Documentation
✨ Core Features
🔌 Call Parameters
claude-sonnet-4-6, cometapi-sonnet-4-6📚 Developer Documentation
📚 Developer Documentation
📚 Developer Documentation
The world's first production-grade model natively designed for Agents. Its Coding & Agentic performance benchmarks directly against Claude Opus 4.6.
📚 Developer Documentation
Zhipu's new generation flagship base model, built for Agentic Engineering. It provides reliable productivity in complex system engineering and long-horizon Agent tasks; the usage experience in real-world coding scenarios approaches Claude Opus 4.5.
📚 Developer Documentation
✨ Core Features
🔌 Call Parameters
claude-opus-4-6 ,cometapi-opus-4-6📚 Developer Documentation
✨ Change Details
chatgpt-4o-latest will be discontinued on Feb 17, 2026.gpt-5.2 for most use cases or gpt-5.2-chat-latest for the newest chat improvements.🔌 Recommended Models
gpt-5.2 , gpt-5.2-chat-latest📚 Developer Documentation
⚠️ 2026-02-04
🔄 CometAPI: Doubao Model Update Notice
✨ Change Details
Legacy Deprecation: In compliance with official policy, the Doubao 1.5 / 1.6 Series have been discontinued.
Migration: Please switch to doubao-seed-1.8.
🔌 Recommended Model
Model Name: doubao-seed-1.8
📚 Developer Documentation
qwen3-max-2026-01-23 (General Flagship)
The strongest snapshot of the Qwen3 series, introducing a Deep Reasoning module. Improves complex logic deduction and code refactoring capabilities by 40%. Ideal for research assistance and system-level instructions.
kimi-k2.5 (Long Context)
Kimi's smartest model to date. Built on a native multimodal architecture, supporting both vision and text inputs simultaneously.
deepseek-ocr-2 (Visual Extraction)
Specialized in handwriting and complex table restoration. Eliminates hallucinations in dense formulas and supports direct Markdown/JSON structured output.
👉 API Docs
gpt-5.2-codex (For Professional Code Tasks)gpt-5.2-codex/v1/responses (Note: This endpoint must be used for this model.)1️⃣ Doubao-Seed-1.8 (Multimodal)
Deep reasoning and powerful multimodal understanding
doubao-seed-1-8-251228/v1/chat/completions2️⃣ Kling 2.6 (Video Generation)
Cinematic quality with native audio synthesis and audio-visual synchronization
kling-v2-6📅 2026-01-04
🚀 Multiple Access Methods Now Available:
🔹 Compatible Format
black-forest-labs/flux-2-max🔹 BFL Native Format
flux-2-max💡 FLUX 2 MAX Core Highlights:
🎯 Ultimate Complex Editing Capabilities
🛍️ E-commerce Photography Revolution: From 0 to 1
🎬 Cinematic-Grade Keyframe Generation
🎨 Hex-Code Level Color Control
👓 Single-Image 3D View Generation
🌐 Real-Time Info Driven Creation
1️⃣ Multimodal Conversation Model
gemini-3-flash✅ Recommended Endpoint:
/v1/chat/completions1️⃣ Image Generation Model
gpt-image-1.5/v1/images/generations⚡️ Key Features: Comprehensive performance upgrade! Pro version delivers ultimate logical reasoning & stability; Chat Latest features an up-to-date knowledge base.
💎 New Models & Integration Guide:
1️⃣ Standard / Latest
gpt-5.2gpt-5.2-chat-latest/v1/chat , /v1/responses2️⃣ Pro Version
gpt-5.2-pro/v1/responses (MUST use this endpoint)🚀 Fully available now. Happy coding!
deepseek-v3.2doubao-seedream-4-5-251128⚠️ gpt-4o-realtime-preview-2024-10-01 will be deprecated on December 3, 2025.
gpt-realtimeAccording to the latest official notifications from Anthropic and Google, our platform will officially deprecate the legacy Claude 3 Series and Gemini 2.5 Preview Series Seriesmodels on December 1st at 00:00. To avoid API call failures, please ensure you switch to the following Model IDs before the deadline:
| Version | Please replace with new Model ID |
|---|---|
| Intelligent (Sonnet) | claude-sonnet-4-5-20250929 |
| Most Powerful (Opus) | claude-opus-4-5-20251101 |
| Fastest (Haiku) | claude-haiku-4-5-20251001 |
| Version | Please replace with new Model ID |
|---|---|
| Standard (Flash) | gemini-2.5-flash |
| Image Enhanced | gemini-2.5-flash-image or gemini-3-pro-image-preview |
| Professional (Pro) | gemini-2.5-pro or gemini-3-pro-preview |
⚠️ Note: The old models will cease to function immediately after December 1st. Please migrate as soon as possible to ensure business continuity.
📅 2025-11-26
🚀 Now Supporting Asynchronous Format Models:
🔹 black-forest-labs/flux-2-pro
🔹 black-forest-labs/flux-2-dev
🔹 black-forest-labs/flux-2-flex
💰 Limited Time Promotion: Lower than Replicate Official Pricing!
💡 FLUX.2 Key Highlights:
🖼️ Multi-Reference Editing: Supports 8-10 reference images to satisfy complex character generation needs.
📸 Ultra-High Quality: Up to 4MP resolution for ultimate natural realism.
⚡ Flexible Selection:
• Pro: Designed for high-efficiency production and fast delivery.
• Flex: Maximizes image quality with adjustable parameters.
• Dev: Developer-friendly optimization.
👇 Start Building Now
Create Predictions - API Doc
🌟 2025-11-25
🎉 CometAPI Launches Claude Opus 4.5 Series!
🚀 Available Models:
🔹 claude-opus-4-5-20251101-thinking
🔹 claude-opus-4-5-20251101
🔹 cometapi-opus-4-5-20251101-thinking
🔹 cometapi-opus-4-5-20251101
💡 Why Claude Opus 4.5?
Top choice for intensive reasoning, code automation, and complex Agent systems.
✨ Key Highlights:
🧠 Superior Reasoning: Handles complex logic.
📝 Automation: Enterprise-grade efficiency.
🤖 Agents: Advanced tool integration.
⚡ Stability: Reliable long-context performance.
📖 Documentation:
👉 Chat - API Doc-CometAPI
👉 Anthropic Messages - API Doc-CometAPI
Experience world-class AI capabilities today! 🚀
🔹 gemini-3-pro-image-preview,gemini-3-pro-image
Gemini 3 Pro Image (also known as nanobanana pro) is Google’s flagship image generation model designed for high-fidelity professional workflows. This release introduces "Deep-Context" understanding for highly complex prompts, perfects in-image typography generation, offers distinct object editing without manual masking, and significantly enhances photorealism and lighting physics.
Follows the Google standard format. See details: CometAPI Chat Documentation https://apidoc.cometapi.com/gemini-generates-image-20873272e0
GUIDE：https://apidoc.cometapi.com/guide-to-calling-gemini-2-5-flash-image-1425263m0
🔹 grok-4-1-fast-reasoning, grok-4-1-fast-non-reasoning
A cutting-edge multimodal model designed specifically for high-performance tool calling and complex interaction scenarios. It delivers exceptional logical processing capabilities while maintaining ultra-fast response speeds. Supports a maximum context of 2M tokens.
Flexible Dual Modes:
reasoning: Enhanced logical reasoning, ideal for complex problem-solving.non-reasoning: Optimized for extreme speed, ideal for high-concurrency tasks.Format Support: Chat format
Google's most intelligent model with SOTA (state-of-the-art) reasoning and multimodal understanding capabilities, featuring powerful agentic and vibe coding abilities. Max context: 2M tokens; Knowledge cutoff: January 1, 2025.
Best For: AI agents, code generation, multimodal understanding
Format Support: Chat format
GPT-5.1 is OpenAI's latest flagship model, designed for advanced coding and agent tasks.
gpt-5.1 & gpt-5.1-chat-latest (For Dialogue & General Tasks)gpt-5.1, gpt-5.1-chat-latest/v1/chatgpt-5.1-codex (For Professional Code Tasks)gpt-5.1-codex/v1/responses (Note: This endpoint must be used for this model.)qwen-imageqwen-image-editqwen-image: It is a universal image generation model, mainly used to generate completely new images based on text, emphasizing the ability to create from scratch. It is suitable for scenarios such as creative generation, stylized drawing, and more.
It is trained on large-scale vision-language models, supports multi-language prompts, but its core focus is on generation rather than editing.
qwen-image-edit: An optimized version based on Qwen-Image, specifically tailored for image editing tasks. It features stronger capabilities in local modifications and consistency preservation. It can not only generate new images but also perform precise edits on existing images.
https://apidoc.cometapi.com/image-editsgpt-image-1-minigpt-image-1-mini: OpenAI's cost-effective image generation model, supporting text/image as input and outputting images; suitable for large-scale, cost-sensitive generation scenarios.
The above models follow the OpenAI standard image generation format for calls. For details, refer to: Text-to-Image, https://apidoc.cometapi.com/image-edits
CometAPI Partners with Bria! CometAPI has reached a cooperation with Bria, and in November 2025, bria all interfaces will be freely open to all users for calls. Have a try!
Sora Asynchronous Format Update: CometAPI has completed the replacement of Sora's asynchronous format and no longer supports the open chat format.
sora-2-pro or sora-2 models, which call this interface (official per-second billing): Sora API.sora-2-all or sora-2-pro-all models, which call this interface (billed per item, after discount: sora-2-all: 0.08, sora-2-pro-all: 0.8): Sora All API.k2-thinkingk2-thinking-turbok2-thinking: Moonshot AI's most advanced open reasoning model, extending the K2 series. It is a thinking model with universal Agentic capabilities and reasoning abilities. Supports 256K tokens context window.k2-thinking-turbo: Based on k2-thinking, it provides faster response speeds and higher concurrency capabilities, supporting the same 256K context and reasoning functions, suitable for high-efficiency scenarios.To improve efficiency and stability, we will optimize the Sora-2 invocation method starting from UTC 2025-11-11 8:00.
sora-2-all or sora-2-pro-all to call the asynchronous interface format (notification will be sent as soon as it's live).If you have any questions, please contact customer service. We are committed to providing a better experience—thank you for your support!
We've added three powerful AI models, all supporting chat format calls to accelerate your AI application development!
Claude Haiku 4.5
GLM-4.6
Veo3.1 & Veo3.1-Pro
All models support chat format calls, with Claude models additionally supporting native message format for maximum integration flexibility!
World's most advanced reasoning models with 400k context window
GPT-5 Series: https://apidoc.cometapi.com/response
🚀 All models live now!
We're excited to announce that GPT-5 Pro - OpenAI's most advanced AI model - is now available on CometAPI!
Use the following model names in your API calls:
https://apidoc.cometapi.com/response-18535147e0
Ready to experience the next generation of AI? Start building with GPT-5 Pro today!
CometAPI Now Supports Sora 2 API Calls
We're excited to announce that CometAPI now fully supports OpenAI's latest Sora 2 video generation model! Developers can now easily access this groundbreaking AI video generation technology through our unified API interface.
Sora-2 is now live and compatible with OpenAI Chat Completions. Switch the base URL to CometAPI and use the key obtained from the CometAPI console to make calls.
Minimal example (replace Authorization with your CometAPI key):
bash
curl --location --request POST 'https://api.cometapi.com/v1/chat/completions'
--header 'Authorization: sk-'
--header 'Content-Type: application/json'
--header 'Accept: /'
--header 'Host: api.cometapi.com'
--header 'Connection: keep-alive'
--data-raw '{
"model": "sora-2",
"stream": true,
"messages": [
{
"role": "user",
"content": "Generate a cute kitten sitting on a cloud, cartoon style"
}
]
}'
👉 Visit https://www.cometapi.com to start experiencing Sora 2's powerful capabilities!
For questions, join our Discord community: https://discord.com/invite/HMpuV6FCrG
curl --location 'https://api.cometapi.com/v1/responses'
--header 'Authorization: Bearer sk-xxxxx'
--header 'Content-Type: application/json'
--data '{
"model": "o3-deep-research-2025-06-26",
"stream": true,
"reasoning": {
"summary": "detailed"
},
"tools": [
{
"type": "web_search_preview"
}
],
"input": "who are you"
}'
Add power to your development workflow. We're excited to announce that CometAPI now fully supports the powerful Claude Code.
What does this mean for you?
Ready to build faster? Please click on the link below to make a call.